karmanov are with you as before.der, if i generated. then, when i am his masterpiece, i always want, no, you always need to mark in the masterpiece, here you will create something good, and then, is it possible to read from the data of this masterpiece, well let's say i forward it, it ends up in someone's use, can i open it and see all the data, how the iteration took place, that is, or is it already blocked, everything, this is not really how the generation took place, you can see, of course, that is, as a specialist, i'm not. i can also tell you on my fingers, imagine how a person creates a picture, any, any image, any painting, he has some white canvas, well, not necessarily white, well, just white paper, some empty, a napkin, a napkin, yes, there is a tablet screen, he has some kind of idea is a must, he starts sketching out some details, with a pen, uh, a stylus, whatever, he adds details, maybe removes something, well, a person also has patterns in his head, that is, he remembered something, he has, he starts d

karmanov, ceo of the presidential fund for cultural initiatives.t of the creative industry on channel one. see you. hello, i'm dmitry. we have another episode of the literary podcast right here: let them not talk, let them read. we we are talking about very different writers, about classics, about our contemporaries, but today we are talking about a person who passed away quite a long time ago, but his prose, his stories, his larger works are still very relevant, they are still debated, their titles are remembered. these are, for example, stories like nervous people, like banya, many others, you have certainly guessed that we are talking about mikhail mikhailovich zoshchenko, he would have turned 130 this year on august 9, we will talk about him today with vera mikhailovna, zoshchenko, the great-granddaughter of mikhail mikhailovich, actress, tv presenter, hello, vera mikhailovna, hello, and also with maria alexandrovna kotova, head of the scientific. let's start the conversation with this: well, zoshchenko flourished in the twenties, gained fame,

karmanov. zakandinsky already that, that it does better than analogues, let's say, analogues analogues are probably the wrong word, well , it seems, then, neural networks that solve the same problem, generating images from text, for example, although, in what are we cooler, although kondinsky generates videos, now yeah, now, well, that is, already, as if already, we recently presented a model that generates videos, called kandinsky video, although probably it should have been called something like tarkovsky, well, we called kandinsky video, we will continue this line, that's it, but what does better, knows the domestic cultural code better, of course, this is what we actually set for the model, what task, and we will certainly develop this further, what is the problem with russian data , here is knowledge of the russian domain, in that there is russian data, of course, there is less of it in what the model learns on, it learns on data from the internet, that is, on open image pairs. description

karmanov sitting on the jury, he doesn't understand what's going on at all, i have a song about him. that your name is nabil, well, like you are nabil karmanov, and that you are karmanov, your deputy is derzhishirev, but we naturally won't tell these jokes, well, so as not to offend you, lenka, i know how we can win today, how we need to show a number about the most famous sakhalin resident, whom everyone here adores, about valery igorevich lemarenko? and who is this? and who are you talking about? about igor nikolaev, about what other nikolaev? and what lemarenko are you talking about? go away from here, huh? well, now valery igorovich is sitting sad, he hasn't laughed before. neither here nor at home, he doesn't laugh, he has no time for fun at all now, but here it is september 8th. we will see a happy valery, thank you, lyudochka, let's show the number anyway, at the opening of any store. friends, we welcome you to the opening of our new store, right now the most respected person in the city will cut the red ribbon, and what kind of store are you opening, an alcoholic one. so ope

karmanov, ceo of the presidential fund for cultural initiatives. the creative industry on channel one. see you. hello, dear friends, this is the podcast life of the remarkable, with you i, its host, writer alexey varlamov. today in this studio i am alone, and my heroine will be a wonderful one of the most fantastic russian women of the silver age nina ivanovna petrovskaya. i don’t know how familiar this name is to you, but i assure you that her fate is extremely curious and instructive. sometimes she was compared to nastasya filippovna from dostoevsky’s novel the idiot. sometimes scarman. well , or scarman, but it seems to me that the most accurate parallel that could be drawn here would be to recall her namesake, nina zarechnaya from chekhov’s the seagull, and that is precisely the fate of this remarkable, sensitive girl who decided to become an actress, who fell in love with an elderly, talented writer, and whose life in general turned out to be broken, did not work out, to some extent. it was this chekhov play that predicted the fate of nina pet

karmanov, and what successes are recognized as zakandinsky already, that's what, what he does betteron his word, well, it seems, then on eroset, which solve the same problem, generating images from text, for example, although, in what we are cooler, although kandinsky videos are generated now, yeah, now. well, that is , as if we have already recently presented a model that generates videos, called kandinsky video, although probably it was necessary to call it something like torkovskiy, well, we called kandinsky video, we will continue this line, but what does it do better, knows the domestic cultural code better, of course, is that we actually set some task for the model, and we certainly we will develop this further, what is the problem with russian data... knowledge of the russian domain is that there is russian data, of course, less of it, what the model learns from, it learns.